Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    maintainduplicarlearningentailproblémy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stalwart
    0.42
    ūd
    0.41
     reimag
    0.41
     Powered
    0.40
     David
    0.40
     Clamp
    0.40
     потребу
    0.40
     Samuel
    0.39
     Абра
    0.39
     pairing
    0.39
    POSITIVE LOGITS
     consultas
    0.40
    エラー
    0.40
    욜
    0.39
    自分の
    0.39
    orrh
    0.39
     obtenir
    0.39
     reciente
    0.39
     problémy
    0.38
     keg
    0.38
     contratos
    0.38
    Act Density 0.001%

    No Known Activations